{"total":43,"rows":[{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154,"area":"alignment"},{"id":"2402.05133","title":"Personalized Language Modeling from Personalized Human Feedback","created":"2024-02-06","cited_by_count":132,"area":"alignment"},{"id":"2311.04155","title":"Black-Box Prompt Optimization: Aligning Large Language Models without Model Training","created":"2023-11-07","cited_by_count":122,"area":"alignment"},{"id":"2310.15140","title":"AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models","created":"2023-10-23","cited_by_count":111,"area":"alignment"},{"id":"2310.09520","title":"Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model","created":"2023-10-14","cited_by_count":79,"area":"alignment"},{"id":"2410.09760","title":"Targeted Vaccine: Safety Alignment for Large Language Models against Harmful Fine-Tuning via Layer-wise Perturbation","created":"2024-10-13","cited_by_count":37,"area":"alignment"},{"id":"2403.14221","title":"Improving the Robustness of Large Language Models via Consistency Alignment","created":"2024-03-21","cited_by_count":36,"area":"alignment"},{"id":"2405.17346","title":"Prompt Optimization with Human Feedback","created":"2024-05-27","cited_by_count":35,"area":"alignment"},{"id":"2306.00398","title":"Preference-grounded Token-level Guidance for Language Model Fine-tuning","created":"2023-06-01","cited_by_count":31,"area":"alignment"},{"id":"2310.05782","title":"Aligning Language Models with Human Preferences via a Bayesian Approach","created":"2023-10-09","cited_by_count":27,"area":"alignment"},{"id":"2309.09055","title":"Exploring the impact of low-rank adaptation on the performance, efficiency, and regularization of RLHF","created":"2023-09-16","cited_by_count":20,"area":"alignment"},{"id":"2410.17875","title":"Understanding Layer Significance in LLM Alignment","created":"2024-10-23","cited_by_count":19,"area":"alignment"},{"id":"2402.11711","title":"MORL-Prompt: An Empirical Analysis of Multi-Objective Reinforcement Learning for Discrete Prompt Optimization","created":"2024-02-18","cited_by_count":16,"area":"alignment"},{"id":"2406.04879","title":"A Deep Dive into the Trade-Offs of Parameter-Efficient Preference Alignment Techniques","created":"2024-06-07","cited_by_count":16,"area":"alignment"},{"id":"2410.10862","title":"Superficial Safety Alignment Hypothesis","created":"2024-10-07","cited_by_count":14,"area":"alignment"},{"id":"2506.12109","title":"Personalized LLM Decoding via Contrasting Personal Preference","created":"2025-06-13","cited_by_count":12,"area":"alignment"},{"id":"2406.12606","title":"Not Everything is All You Need: Toward Low-Redundant Optimization for Large Language Model Alignment","created":"2024-06-18","cited_by_count":7,"area":"alignment"},{"id":"2410.11370","title":"Enhance Graph Alignment for Large Language Models","created":"2024-10-15","cited_by_count":7,"area":"alignment"},{"id":"2505.23473","title":"EVOREFUSE: Evolutionary Prompt Optimization for Evaluation and Mitigation of LLM Over-Refusal to Pseudo-Malicious Instructions","created":"2025-05-29","cited_by_count":6,"area":"alignment"},{"id":"2503.16094","title":"Cultural Alignment in Large Language Models Using Soft Prompt Tuning","created":"2025-03-20","cited_by_count":5,"area":"alignment"},{"id":"2508.17184","title":"Towards Alignment-Centric Paradigm: A Survey of Instruction Tuning in Large Language Models","created":"2025-08-24","cited_by_count":5,"area":"alignment"},{"id":"2512.23260","title":"Interpretable Safety Alignment via SAE-Constructed Low-Rank Subspace Adaptation","created":"2025-12-29","cited_by_count":5,"area":"alignment"},{"id":"2310.00819","title":"Parameter-Efficient Tuning Helps Language Model Alignment","created":"2023-10-01","cited_by_count":4,"area":"alignment"},{"id":"2412.20834","title":"Disentangling Preference Representation and Text Generation for Efficient Individual Preference Alignment","created":"2024-12-30","cited_by_count":4,"area":"alignment"},{"id":"2503.20194","title":"GAPO: Learning Preferential Prompt through Generative Adversarial Policy Optimization","created":"2025-03-26","cited_by_count":4,"area":"alignment"},{"id":"2406.11039","title":"Dynamic Normativity: Necessary and Sufficient Conditions for Value Alignment","created":"2024-06-16","cited_by_count":3,"area":"alignment"},{"id":"2601.06352","title":"CARD: Cluster-level Adaptation with Reward-guided Decoding for Personalized Text Generation","created":"2026-01-09","cited_by_count":3,"area":"alignment"},{"id":"2406.16377","title":"On the Transformations across Reward Model, Parameter Update, and In-Context Prompt","created":"2024-06-24","cited_by_count":1,"area":"alignment"},{"id":"2408.02651","title":"Can Reinforcement Learning Unlock the Hidden Dangers in Aligned Large Language Models?","created":"2024-08-05","cited_by_count":1,"area":"alignment"},{"id":"2602.03073","title":"TMS: Trajectory-Mixed Supervision for Reward-Free, On-Policy SFT","created":"2026-02-03","cited_by_count":1,"area":"alignment"},{"id":"2603.05231","title":"Boosting ASR Robustness via Test-Time Reinforcement Learning with Audio-Text Semantic Rewards","created":"2026-03-05","cited_by_count":1,"area":"alignment"},{"id":"2607.29246","title":"Don't Mix Rewards, Mix Policies: Policy Decomposition and Optimization for Multi-Reward RL","created":"2026-07-31","cited_by_count":1,"area":"alignment"},{"id":"2506.09329","title":"Towards Efficient and Effective Alignment of Large Language Models","created":"2025-06-11","cited_by_count":0,"area":"alignment"},{"id":"2601.09718","title":"StatLLaMA: Multi-Stage training for domain-optimized statistical large language models","created":"2025-12-26","cited_by_count":0,"area":"alignment"},{"id":"2601.11574","title":"GRADE: Replacing Policy Gradients with Backpropagation for LLM Alignment","created":"2025-12-30","cited_by_count":0,"area":"alignment"},{"id":"2604.17210","title":"Guardrails in Logit Space: Safety Token Regularization for LLM Alignment","created":"2026-04-19","cited_by_count":0,"area":"alignment"},{"id":"2605.09777","title":"EvoPref: Multi-Objective Evolutionary Optimization Discovers Diverse LLM Alignments Beyond Gradient Descent","created":"2026-05-10","cited_by_count":0,"area":"alignment"},{"id":"2605.11712","title":"Toward Stable Value Alignment: Introducing Independent Modules for Consistent Value Guidance","created":"2026-05-12","cited_by_count":0,"area":"alignment"},{"id":"2606.13227","title":"PolyAlign: Conditional Human-Distribution Alignment","created":"2026-06-11","cited_by_count":0,"area":"alignment"},{"id":"2607.28669","title":"LARA: Lightweight Adapters in the Residual Stream for Composable Adaptation and Alignment","created":"2026-07-25","cited_by_count":0,"area":"alignment"},{"id":"2608.09605","title":"TSPORec: Token Selection via Preference Optimization for LLM-Based Sequential Recommendation","created":"2026-08-10","cited_by_count":0,"area":"alignment"},{"id":"2608.13069","title":"Behavioral Reprogramming of Open-Weights Models: Cognitive Plasticity and Alignment Bounds","created":"2026-08-13","cited_by_count":0,"area":"alignment"},{"id":"2609.07808","title":"You Can't Prefer Emotions You Don't Sample: Intensity Undershoot in DPO-Tuned LLMs","created":"2026-09-07","cited_by_count":0,"area":"alignment"}],"next_cursor":null}